© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 35358
    Prev
    Next
    INDEX
    Explanations

    regular grant kind each more

    np_acts-logits-general · gemini-2.5-flash-lite

    called Campus graffiti

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iteratively
    0.48
    RENGTH
    0.46
    有望
    0.45
    attuale
    0.44
    ∪
    0.43
     スター
    0.42
     危
    0.42
     accomplishes
    0.42
     insufficiency
    0.42
     लेती
    0.40
    POSITIVE LOGITS
     Campus
    0.48
     llamados
    0.44
     Graffiti
    0.43
     graffiti
    0.43
     ক্যাম্পাস
    0.42
    逍
    0.41
     peppermint
    0.41
    कायदा
    0.41
     teníamos
    0.40
    called
    0.40
    Activations Density 0.000%

    No Known Activations